1.Determination of Sputum Suction Timing in Mechanical Ventilation Based on Transfer Learning and Breath Sounds Recognition
Shuai WANG ; Jiangzhen GUO ; Chunjing TAO
Journal of Medical Biomechanics 2025;40(5):1318-1324
Objective To propose a transfer learning-based method for breath sound feature recognition and autonomous determination of sputum suction timing.Methods An electronic stethoscope was used to collect breath sounds from the main airways of clinically ventilated patients before and after sputum suction,with pre-suction breath sounds labeled as requiring suction.The collected data underwent high-pass filtering and wavelet soft-threshold denoising,followed by the extraction of log-Mel spectrograms.A VGGish model pretrained on the Audio Set dataset was then employed to extract feature vectors from these spectrograms,which were subsequently classified using a support vector machine to determine whether suction was required.Results The precision,recall and F1 score for recognition of breath sounds requiring sputum suction were 86.73%,93.06%and 89.78%,respectively.Conclusions The proposed breath sound recognition method based on transfer learning effectively determines the timing of sputum suction and shows a significant clinical potential.
2.Determination of Sputum Suction Timing in Mechanical Ventilation Based on Transfer Learning and Breath Sounds Recognition
Shuai WANG ; Jiangzhen GUO ; Chunjing TAO
Journal of Medical Biomechanics 2025;40(5):1318-1324
Objective To propose a transfer learning-based method for breath sound feature recognition and autonomous determination of sputum suction timing.Methods An electronic stethoscope was used to collect breath sounds from the main airways of clinically ventilated patients before and after sputum suction,with pre-suction breath sounds labeled as requiring suction.The collected data underwent high-pass filtering and wavelet soft-threshold denoising,followed by the extraction of log-Mel spectrograms.A VGGish model pretrained on the Audio Set dataset was then employed to extract feature vectors from these spectrograms,which were subsequently classified using a support vector machine to determine whether suction was required.Results The precision,recall and F1 score for recognition of breath sounds requiring sputum suction were 86.73%,93.06%and 89.78%,respectively.Conclusions The proposed breath sound recognition method based on transfer learning effectively determines the timing of sputum suction and shows a significant clinical potential.

Result Analysis
Print
Save
E-mail